© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 21992
    Prev
    Next
    INDEX
    Explanations

    occurrences of ellipses (...) indicating a trailing off or unfinished thought

    oai_token-act-pair · gpt-3.5-turbo

    ellipses or trailing dots indicating continuation or omission in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -1.01
    uers
    -0.78
     purse
    -0.78
     lip
    -0.77
     critically
    -0.74
     wealthier
    -0.69
     diseng
    -0.69
     greens
    -0.68
    ãĥ³ãĤ¸
    -0.67
    opol
    -0.67
    POSITIVE LOGITS
    etc
    1.07
     ..........
    0.87
    quote
    0.82
    orders
    0.81
    uga
    0.79
     ..
    0.78
    walking
    0.78
    where
    0.78
    ...]
    0.77
     fixme
    0.77
    Activations Density 0.008%

    No Known Activations